Push Reinforce agent to the Hub
Browse files- .gitattributes +1 -0
- README.md +27 -0
- hyperparameters.json +1 -0
- model.pt +3 -0
- replay.mp4 +3 -0
- results.json +1 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- Pixelcopter-PLE-v0
|
4 |
+
- reinforce
|
5 |
+
- reinforcement-learning
|
6 |
+
- custom-implementation
|
7 |
+
- deep-rl-class
|
8 |
+
model-index:
|
9 |
+
- name: RL_course_unit4_part1
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: Pixelcopter-PLE-v0
|
16 |
+
type: Pixelcopter-PLE-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: -5.00 +/- 0.00
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
|
25 |
+
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
|
26 |
+
To learn to use this model and train yours check Unit 5 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
|
27 |
+
|
hyperparameters.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
|
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0057cd0c03b2b952349267427511c46b70e63ab2b45ebf5280334ef645c2268f
|
3 |
+
size 2771
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:583a0def70a917584a0cd824006453f6b89664a5fd2caa64312529e3463ea3bd
|
3 |
+
size 2436
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-23T09:39:17.961486"}
|